Metadata-Version: 2.4
Name: miles-credit
Version: 2026.2.0
Author-email: "NCAR Machine Integration and Learning for Earth Systems (MILES)" <miles@ucar.edu>
License: Apache-2.0
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: pandas<3.0.4
Requires-Dist: matplotlib
Requires-Dist: cartopy
Requires-Dist: scikit-learn
Requires-Dist: h5py<=3.14.0
Requires-Dist: pyarrow
Requires-Dist: xarray
Requires-Dist: netcdf4
Requires-Dist: h5netcdf
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: einops
Requires-Dist: pyyaml
Requires-Dist: zarr
Requires-Dist: pygrib
Requires-Dist: numcodecs
Requires-Dist: echo-opt
Requires-Dist: bridgescaler
Requires-Dist: segmentation-models-pytorch
Requires-Dist: haversine
Requires-Dist: pvlib
Requires-Dist: torch-harmonics<0.9
Requires-Dist: torch_geometric
Requires-Dist: torchmetrics
Requires-Dist: fsspec
Requires-Dist: gcsfs
Requires-Dist: s3fs
Requires-Dist: obstore
Requires-Dist: setuptools_scm
Requires-Dist: setuptools
Requires-Dist: numba
Requires-Dist: tensorboard
Requires-Dist: fastapi
Requires-Dist: overrides
Provides-Extra: docs
Requires-Dist: sphinx; extra == "docs"
Requires-Dist: sphinx-autoapi; extra == "docs"
Requires-Dist: myst_parser; extra == "docs"
Requires-Dist: sphinx-book-theme; extra == "docs"
Requires-Dist: sphinx-design; extra == "docs"
Provides-Extra: develop
Requires-Dist: pre-commit; extra == "develop"
Requires-Dist: sphinx; extra == "develop"
Requires-Dist: sphinx-autoapi; extra == "develop"
Requires-Dist: myst_parser; extra == "develop"
Requires-Dist: sphinx-book-theme; extra == "develop"
Requires-Dist: sphinx-design; extra == "develop"
Requires-Dist: jupyter; extra == "develop"
Requires-Dist: ruff; extra == "develop"
Requires-Dist: pytest; extra == "develop"
Provides-Extra: ptype
Requires-Dist: metpy; extra == "ptype"
Requires-Dist: miles-guess; extra == "ptype"
Requires-Dist: keras; extra == "ptype"
Provides-Extra: ask
Requires-Dist: anthropic>=0.40; extra == "ask"
Requires-Dist: groq>=0.9; extra == "ask"
Requires-Dist: openai>=1.0; extra == "ask"
Requires-Dist: google-generativeai>=0.8; extra == "ask"
Provides-Extra: agent
Requires-Dist: anthropic>=0.40; extra == "agent"
Dynamic: license-file

# NSF NCAR MILES Community Research Earth Digital Intelligence Twin (CREDIT)

[![DOI](https://zenodo.org/badge/710968229.svg)](https://doi.org/10.5281/zenodo.14361005)

[PyPI](https://pypi.org/project/miles-credit/)

[CREDIT npj Climate and Atmospheric Science Article](https://www.nature.com/articles/s41612-025-01125-6)

## About
CREDIT is an open software platform to train and deploy AI atmospheric prediction models. CREDIT offers fast models
that can be flexibly configured both in terms of input data and neural network architecture. The interface is designed
to be user-friendly and enable fast spin-up and iteration. CREDIT is backed by the AI and atmospheric science expertise
of the MILES group and the NSF National Center for Atmospheric Research, leading to design choices that balance advanced
AI/ML with our physical knowledge of the atmosphere.

CREDIT has reached its first stable release with a full set of models, training, and deployment options. It continues
to be under active development. Please contact [the MILES group](mailto:milescore@ucar.edu) if you have any questions about CREDIT.

**New to CREDIT?** See [QUICKSTART.md](QUICKSTART.md) to get up and running locally, or the [full online Quickstart](https://miles-credit.readthedocs.io/en/latest/quickstart.html) for detailed guidance.

## Getting started

Install CREDIT and launch the interactive config wizard:

```bash
conda create -n credit -y python=3.13 uv
conda activate credit
uv pip install miles-credit
credit begin
```

`credit begin` walks you through creating a starter config, then validates it
with `credit check` and prints the `credit preprocess` / `credit train`
commands to run next. See [QUICKSTART.md](QUICKSTART.md) for the NCAR
Casper/Derecho install paths and the rest of the workflow.

## Documentation

The [full documentation](https://miles-credit.readthedocs.io/en/latest/) covers installation,
training and deploying models, the config file schema, datasets, and the gen2 pipeline, along
with complete [API docs](https://miles-credit.readthedocs.io/en/latest/api/index.html).

## Citing CREDIT
If you are interested in using CREDIT as part of your research, please cite the following paper:
Schreck, J.S., Sha, Y., Chapman, W. et al. Community Research Earth Digital Intelligence Twin: a scalable framework 
for AI-driven Earth System Modeling. npj Clim Atmos Sci 8, 239 (2025). https://doi.org/10.1038/s41612-025-01125-6

# Model Weights and Data
Model weights for the CREDIT 6-hour WXFormer and FuXi models, the 1-hour WXFormer, and the CAMulator climate emulator are available on huggingface.

* [6-Hour WXFormer](https://huggingface.co/djgagne2/wxformer_6h)
* [1-Hour WXFormer](https://huggingface.co/djgagne2/wxformer_1h)
* [6-Hour FuXi](https://huggingface.co/djgagne2/fuxi_6h)
* [CAMulator](https://huggingface.co/willychap/camulator)

Processed ERA5 Zarr Data are available for download through Globus (requires free account) through the [CREDIT ERA5 Zarr Files](https://app.globus.org/file-manager/collections/2fc90d8f-10b7-44e1-a6a5-cf844112822e/overview) collection.

Scaling/transform values for normalizing the data are available through Globus [here](https://app.globus.org/file-manager/collections/c5a23e21-1bee-4d1e-bb59-77c5dcee7c76). 

CREDIT also supports realtime runs generated from deterministic [Google Cloud GFS files](https://console.cloud.google.com/marketplace/product/noaa-public/gfs)
and raw cube sphere [GEFS files](https://console.cloud.google.com/marketplace/product/noaa-public/gfs-ensemble-forecast-system).

# Support
This software is based upon work supported by the NSF National Center for Atmospheric Research, a major facility sponsored by the 
U.S. National Science Foundation  under Cooperative Agreement No. 1852977 and managed by the University Corporation for Atmospheric Research. Any opinions, findings and conclusions or recommendations 
expressed in this material do not necessarily reflect the views of NSF. Additional support for development was provided by 
The NSF AI Institute for Research on Trustworthy AI for Weather, Climate, and Coastal Oceanography (AI2ES)  with grant
number RISE-2019758, NSF Grant [RISE-2425659](https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2425659), and by Schmidt Sciences, LLC. 
